INDEX

Explanations

code declarations and type definitions related to threading and data structures

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

há

-0.52

 MonoBehaviour

-0.51

 aDecoder

-0.49

poor

-0.49

 poor

-0.49

Poor

-0.48

cences

-0.48

ente

-0.48

bad

-0.47

cente

-0.47

POSITIVE LOGITS

RunWith

0.82

InjectAttribute

0.79

 typelib

0.78

出版年

0.76

 فريبيس

0.71

 שוליים

0.69

 ujednoznacz

0.65

SourceChecksum

0.61

ViewFeatures

0.61

LikeLike

0.59

Activations Density 0.410%

code declarations and type definitions related to threading and data structures

No Comments

No Known Activations